COMPUTATIONAL EXPERIMENTS WITH A FEATURE BASED STEREO ALGORITHM
COMPUTATIONAL EXPERIMENTS WITH A FEATURE BASED STEREO ALGORITHM
复制标题
DOI：
10.1109/tpami.1985.4767615
复制
发表时间：
1985-01-01
影响因子：
23.6
通讯作者：
GRIMSON, WEL
中科院分区：
文献类型：
--
作者：
GRIMSON, WEL
人类立体声系统的计算模型可以提供对适用于任何立体声系统（无论是人工的还是生物的）的一般信息处理约束的洞察。1977年，马尔和Poggio提出了一个这样的计算模型，其特征在于匹配高斯差分滤波图像中的某些特征点，并使用通过匹配较粗分辨率表示获得的信息来限制匹配较细分辨率表示的搜索空间。1980年报道了该算法的实现及其在一系列图像上的测试。从那时起，许多心理物理学实验提出了对模型的可能改进和对算法的修改。此外，最近的计算实验，应用该算法的各种自然图像，特别是航空照片，导致了一些修改。在本文中，我们提出了一个版本的Marr-Poggio-Grimson算法，体现了这些修改，我们说明了它的一系列自然图像上的性能。
Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977 Marr and Poggio proposed one such computational model, which was characterized as matching certain feature points in difference-of-Gaussian filtered images and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Since then a number of psychophysical experiments have suggested possible refinements to the model and modifications to the algorithm. As well, recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this paper, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and we illustrate its performance on a series of natural images.